Statistical modeling of co-articulation in continuous speech based on data driven interpolation

Parsimonious modeling of the context dependency nature of speech due to co-articulation is very important for improving the performance of speech recognition systems. Numerous approaches have been proposed in the literature to address this problem. However, most of the methods are based on the idea of using context-dependent speech units, which inevitably increases the complexity of the model space. This paper presents a new approach of speech co-articulation modeling with complexity only comparable to context-independent models. In this model, the movement of a sequence of speech signals is characterized by a set of anchor points in the feature vector space that correspond to the target phonemic units. The transitions between the phonemic units due to co-articulation are modeled as interpolations between the target vectors. Two types of parameters are involved in the models: the intrinsic parameters in the models of target units and the auxiliary parameters specifying the transitional units. The auxiliary parameters are estimated "online" for a given sequence of speech feature vectors, hence it does not contribute to the complexity of the models. Unlike "triphone"-type context dependent models, the complexity of this approach is comparable to the context independent phoneme models, yet, some phonetic classification experiments showed that the new model can achieve the same performance as the more complex context dependent models.